Indeed Employee Review data analysis of company Northwestern Mutual

libraries used.

library(dplyr)

Attaching package: 㤼㸱dplyr㤼㸲

The following objects are masked from 㤼㸱package:plyr㤼㸲:

    arrange, count, desc, failwith, id, mutate, rename, summarise, summarize

The following object is masked from 㤼㸱package:gridExtra㤼㸲:

    combine

The following objects are masked from 㤼㸱package:igraph㤼㸲:

    as_data_frame, groups, union

The following objects are masked from 㤼㸱package:stats㤼㸲:

    filter, lag

The following objects are masked from 㤼㸱package:base㤼㸲:

    intersect, setdiff, setequal, union

Data Mining from Indeed Website

ht<-list(c())
n=seq(0,2835,20)
for(i in n){
y=read_html(paste("https://www.indeed.co.in/cmp/Northwestern-Mutual/reviews?fcountry=ALL&start=i"))%>% html_nodes(".cmp-review-text")%>%html_text(trim = TRUE)
ht<-append(ht,x)
}

#Data-Preprocessing: removing '\n'
FCA_html<-gsub("\n","",FCA_html)
#remove all round brackets
FCA_html<-FCA_html%>%str_replace_all("\\(|\\)", "")
#remove all \\
FCA_html<-FCA_html%>%str_replace_all("\\\\", "")
#remove all non words and non numbers
#FCA_html<-FCA_html%>%str_replace_all("[^A-Za-z0-9]", "")
#remove all • 
FCA_html<-FCA_html%>%str_replace_all("\\•  ", "")
#remove all & 
FCA_html<-FCA_html%>%str_replace_all("\\ & ", "")
#remove all  non printable words
FCA_html<-FCA_html%>%str_replace_all("[^[:print:]]", "")
#remove all \
FCA_html<-FCA_html%>%str_replace_all(pattern = "\"", replacement = "")
#FCAindeed2<-FCAindeed2%>%stringi::stri_unescape_unicode()
# remove digits
#FCA_html%>%str_replace_all(pattern = "[[:digit:]]+", replacement = "")
#tm::removeNumbers(FCA_html)
#### pattern for dates
pattern ="\\(?\\d{4}\\)?[.-]? *\\d{2}[.-]? *[.-]?\\d{2}"
date=FCA_html%>%str_extract_all(pattern)
#FCA_html[[1]]%>%str_subset(pattern = "([0-9]{1,2})[- .]([a-zA-Z]+)[- .]([0-9]{4})")
#FCA_html[[1]]
#unlist(Date)
#FCA_html_2=data_frame(Date=as.Date(unlist(date)),FCA_html)

indeed <- tibble(text = c(FCA_html))

#convert all text to lower case
df_lower<- tolower(indeed$text)
# Replace blank space (“rt”)
df_lower <- gsub("rt", "", df_lower)
# Replace @UserName
df_lower <- gsub("@\\w+", "", df_lower)
# Remove punctuation
df_lower <- gsub("[[:punct:]]", "", df_lower)
# Remove links
df_lower <- gsub("http\\w+", "", df_lower)
# Remove tabs
df_lower<- gsub("[ |\t]{2,}", "", df_lower)
# Remove blank spaces at the beginning
df_lower <- gsub("^ ", "", df_lower)
# Remove blank spaces at the end
df_lower <- gsub(" $", "",df_lower )

#clean up by removing stop words
corpus<-Corpus(VectorSource(df_lower))
corpus <- tm_map(corpus, function(x)removeWords(x,stopwords()))

transformation drops documents

#generate wordcloud
wordcloud(corpus,min.freq = 10,colors=brewer.pal(8, "Dark2"),random.color = TRUE,max.words = 500)

#getting emotions using in-built function
mysentiment<-get_nrc_sentiment((df_lower))

#calculationg total score for each sentiment
Sentimentscores<-data.frame(colSums(mysentiment[,]))
names(Sentimentscores)<-"Score"
Sentimentscores<-cbind("sentiment"=rownames(Sentimentscores),Sentimentscores)
rownames(Sentimentscores)<-NULL

#plotting the sentiments with scores
ggplotly(ggplot(data=Sentimentscores,aes(x=reorder(sentiment,Score),y=Score))+geom_bar(aes(fill=sentiment),stat = "identity")+
  theme(legend.position="none")+
  xlab("Sentiments")+ylab("scores")+ggtitle("Sentiments of Employees behind the comments or rating ")+labs(title = "Sentiments of people behind the tweets on #MachineLearning",x="Sentiments", y = "Scores")+theme(plot.title = element_text(hjust = -10,face = "bold",color = "black"))+coord_flip())

Finding the words count in the text data.

dtm <- TermDocumentMatrix(corpus)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
d<- d[with(d,order(-freq)),]
head(d, 20)

showing the top 10 high frequency words used in the text.

ggplotly(ggplot(d[1:10,],aes(x=reorder(word,freq),y=freq,fill=as.factor(word)))+geom_bar(stat = "identity")+ geom_text(aes(label=freq), vjust=10)+labs(title = "The Top 10 frequently used words",x="Words", y = "Frequency of Words",fill="Words")+theme(plot.title = element_text(hjust = -10,face = "bold",color = "black"))+coord_flip())

library(data.table)
d<-as.data.table(d)
p <- d[1:10,] %>%
 group_by(word) %>%
 plot_ly(labels = ~word, values = ~d[1:10,freq]) %>%
 add_pie(hole = 0.6) %>%
 layout(title = "The Percentage of top 10 frequently occuring words.",  showlegend = F,
         yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
p